All models
ElevenLabs
Scribe v2
ElevenLabs' multilingual speech-to-text model for detailed transcripts with many speakers, word timing, audio events, and large custom keyterm lists.
Plain-English overview
What Scribe v2 actually is
Scribe v2 turns long audio or video into structured transcripts with language detection, word timestamps, speaker diarization, and audio tags for events beyond speech. Keyterm prompting helps teams preserve names, products, and vocabulary that general recognition models often miss.
ElevenLabs offers file transcription and a separately priced realtime route. The broader platform also provides voice and agent products, which can simplify one-vendor audio pipelines, although each capability has its own billing and data controls.
Good fit for
- Multilingual media transcription
- Recordings with many speakers or sound events
- Audio stacks already using ElevenLabs
Category comparison
The facts that matter for transcription models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Transcription price
- $0.22 / audio hour; realtime listed separatelyCurrent provider price per audio hour or minute for the listed processing route.
- Live or batch
- Batch and long audio; separate realtime routeWhether the model handles realtime streams, uploaded recordings, or both.
- Languages
- 90+ languagesProvider-published language coverage, separating trained or advertised coverage from specifically verified languages where needed.
- Speaker labels
- Up to 32 speakersWhether the model identifies who spoke and any published speaker limit.
- Timestamps
- Word-level timestampsAvailable word-, segment-, or utterance-level timing information.
- Vocabulary control
- Up to 1,000 keyterms; audio tags and language detectionKeyword boosting, custom spelling, context, prompting, or other ways to improve domain terms.
- Where to use it
- ElevenLabs Speech-to-Text APIDirect API, cloud catalog, application, or regional endpoint documented by the provider.
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Uses the recording length in hours: 30 minutes = 0.5 hours. Extra features and minimum charges may change the bill.
Scribe v2
ElevenLabs
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get Scribe v2
Availability
Regions and access stage
Available through the ElevenLabs speech-to-text API and product interfaces; realtime uses a separate model route.
Global and data-residency options depend on the ElevenLabs plan, endpoint, and enterprise configuration.
Check live availabilityData and training
The route matters.
ElevenLabs lets eligible API customers manage data-use preferences. Zero-data-retention through enable_logging=false is limited to qualifying enterprise configurations and supported models, including Scribe v2; verify the live plan and regional endpoint.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Scribe v2 FAQ
What is Scribe v2?
ElevenLabs' multilingual speech-to-text model for detailed transcripts with many speakers, word timing, audio events, and large custom keyterm lists. Scribe v2 turns long audio or video into structured transcripts with language detection, word timestamps, speaker diarization, and audio tags for events beyond speech. Keyterm prompting helps teams preserve names, products, and vocabulary that general recognition models often miss.
When was Scribe v2 released?
Scribe v2 was released on January 9, 2026 according to the cited provider materials.
Where can I access Scribe v2?
Available through the ElevenLabs speech-to-text API and product interfaces; realtime uses a separate model route. The access routes listed in this guide are ElevenLabs and ElevenLabs API.
How much does Scribe v2 cost?
$0.22 / audio hour for Scribe v2. ElevenLabs lists separate pricing for batch Scribe v2 and Scribe v2 Realtime. Entity detection and redaction can be billed separately.
Where is Scribe v2 available?
Available through the ElevenLabs speech-to-text API and product interfaces; realtime uses a separate model route. Global and data-residency options depend on the ElevenLabs plan, endpoint, and enterprise configuration.
Is my Scribe v2 API data used for training?
ElevenLabs lets eligible API customers manage data-use preferences. Zero-data-retention through enable_logging=false is limited to qualifying enterprise configurations and supported models, including Scribe v2; verify the live plan and regional endpoint. The policy belongs to the provider route and account terms, so verify it again before production use.
Related comparisons
Head-to-head comparisons
Scribe v2 vs Muse Voice Transcribe
Meta's streaming speech-recognition model for live captions, long audio, many speakers, code-switching, and domain-aware transcription.
Open full comparisonScribe v2 vs MAI-Transcribe-2
Microsoft's fast batch transcription model for long recordings, speaker labels, word timing, keyword biasing, and clean or verbatim transcripts.
Open full comparisonScribe v2 vs Chirp 3
Google Cloud's general speech-to-text model for streaming, file, and low-cost dynamic-batch transcription across many languages and regions.
Open full comparisonScribe v2 vs Universal-3.5 Pro
AssemblyAI's accuracy-focused transcription model for files and live audio, with code-switching, speaker labels, timestamps, and contextual prompting.
Open full comparison
